Pricing
$30.00/month + usage
Scrapes property data from Savills Auction House. Supports both upcoming and past auction listings from any search result URL, extracting detailed property information efficiently for analysis or automation.
0.0 (0)
Pricing
$30.00/month + usage
0
2
1
Last modified
17 days ago
{ "actorSpecification": 1, "name": "savills-auction-data-scraper", "title": "Savills Auction Data Scraper", "description": "Scrape auctioned property data in Savills.", "version": "0.0", "storages": { "dataset": { "actorSpecification": 1, "fields": {}, "views": { "overview": { "title": "Overview", "transformation": {}, "display": { "component": "table", "properties": { "Page": { "label": "Page", "format": "number" }, "URL": { "label": "URL", "format": "link" }, "AuctionDate": { "label": "AuctionDate", "format": "text" }, "PropertyData": { "label": "PropertyData", "format": "array" } } } } } } }, "meta": { "templateId": "js-crawlee-puppeteer-chrome" }, "input": "./input_schema.json", "dockerfile": "../Dockerfile"}{ "title": "Scrape data from Savills", "type": "object", "schemaVersion": 1, "properties": { "URL": { "title": "URL of the search result page", "type": "string", "description": "The URL of the search result in Savills you want to get the data from.", "editor": "textfield", "prefill": "https://auctions.savills.co.uk/auctions/1-october-2025-194" }, "OutputLimiterEnabled": { "type": "boolean", "title": "Enable Output Limiter?", "description": "If enabled, the Actor will only scrape data equal to the limit set by the user.", "editor": "checkbox", "default": false }, "OutputLimit": { "title": "Output Limit", "type": "integer", "description": "The maximum number of property pages to scrape before stopping.", "editor": "number", "minimum": 1, "maximum": 1000, "default": 2 } }, "required": ["URL"]}1import { Actor } from 'apify';2import { PuppeteerCrawler, Dataset } from 'crawlee';3import log from '@apify/log';4//////////////////////////////////////////////////////////////////////////////////////////////////////////////5//////////////////////////////////////////////////////////////////////////////////////////////////////////////6////* PROJECT : APIFY - SAVILLS AUCTION DATA SCRAPER7////* DESCRIPTION : Scrapes Real Estate property-related data from Savills given auction URL for APIFY8////* AUTHOR : Jeric Cobarrubias9////* CREATION DATE : September 25, 202510////* COPYRIGHT : (c) 2025 TwoCores. All rights reserved.11//////////////////////////////////////////////////////////////////////////////////////////////////////////////12//////////////////////////////////////////////////////////////////////////////////////////////////////////////13await Actor.init();14
15const input = await Actor.getInput();16const { URL, OutputLimiterEnabled, OutputLimit } = input;17//const proxyConfiguration = await Actor.createProxyConfiguration();18let output = [];19
20const BaseURL = "https://auctions.savills.co.uk/";21
22const crawler = new PuppeteerCrawler({23 //proxyConfiguration,24 navigationTimeoutSecs: 600,25 requestHandlerTimeoutSecs: 600,26 requestHandler: async({ page, request }) => {27 await page.content();28 await page.waitForSelector('ul.lots-list', { visible: true });29 log.info("SAVILLS.CO.UK AUCTION DATA SCRAPER");30 const auction_date = await page.$eval('.auction-information__wrapper--left > h1', ($p) => { 31 return $p.innerText;32 });33 log.info("TARGET URL : "+request.url);34 log.info("AUCTION DATE : "+auction_date); 35 let search = await page.$eval('ul.lots-list', e => {36 e.children[1].querySelector('div.lot-right > div.lot-content > a.lot-name').click();37 });38 39 let count = 0;40 let nextPage = true;41 while(nextPage)42 {43 await page.waitForNavigation(0);44 await page.waitForSelector('.lot-details-inner', { visible: true });45 count++;46 log.info(`SCRAPING PAGE ${count}. PROPERTY URL : ${page.url()}`);47 const pR_Data = await page.$eval('.lot-details-inner', property => {48 const data = [];49 const prop_lot_info = property.querySelector('.sv-property-intro__address-block > h4')50 const prop_address_1 = property.querySelector('h1.sv-property-intro__address-line-1')51 const prop_address_2 = property.querySelectorAll('span.sv-property-intro__address-line-2')52 const prop_guide_price = property.querySelector('span.sv-property-price__value > span:not([class])')53 const prop_sell_value = property.querySelector('span.sv-property-price__value > span.value')54 const prop_status = property.querySelector('div.lot-status-container')55 const prop_key_features = property.querySelectorAll('div.sv-key-features > ul > li')56 const prop_description = property.querySelector('div.lot-details-description')57 const prop_exData = property.querySelector('div.additional-container')58 59 let prop_address = "";60 prop_address_2.forEach(address_line => { prop_address = prop_address + address_line.innerText; });61 62 const features = [];63 prop_key_features.forEach(item => { features.push(item.innerText); });64 65 data.push({66 LotInfo : prop_lot_info ? prop_lot_info.innerText : null,67 AddressLine1 : prop_address_1 ? prop_address_1.innerText : null,68 AddressLine2 : prop_address ? prop_address : null,69 GuidePrice : prop_guide_price ? prop_guide_price.innerText : null,70 SellValue : prop_sell_value ? prop_sell_value.innerText : null,71 Status : prop_status ? prop_status.innerHTML.toString().replaceAll(/<[^>]*>/g, '') : null,72 KeyFeatures : features.length > 0 ? features : null,73 Description : prop_description ? prop_description.innerHTML.toString().replaceAll('</p>','/n').replaceAll(/<[^>]*>/g, '') : null,74 ExtraData : prop_exData ? prop_exData.innerHTML.toString().replaceAll('</p>','/n').replaceAll(/<[^>]*>/g, '') : null75 });76 return data;77 }); 78 output.push({79 Page : count,80 URL : page.url(),81 AuctionDate : auction_date,82 PropertyData : pR_Data});83 84 if(OutputLimiterEnabled)85 {86 if(count == OutputLimit)87 break;88 }89 nextPage = await page.$eval('div.lot-details-controls--top-right', pagination => {90 const b_next = pagination.querySelector('.nextLot');91 if (b_next) {92 b_next.click();93 return true;94 } else {95 return false;96 }97 });98 }99 },100 async failedRequestHandler({ request }) {101 await Dataset.pushData({102 url: request.url,103 succeeded: false,104 errors: request.errorMessages,105 })106 },107 launchContext: {108 launchOptions: {109 args: [110 '--disable-gpu',111 '--no-sandbox',112 ],113 },114 },115});116
117if (URL.toLowerCase().includes(BaseURL)){118 await crawler.run([URL]);119 console.log('Crawler finished.');120 await Actor.pushData(output);121} else {122 log.error("Invalid URL: ", URL);123}124await Actor.exit();1import { createPuppeteerRouter, Dataset } from 'crawlee';2
3export const router = createPuppeteerRouter();4
5router.addDefaultHandler(async ({ enqueueLinks, log }) => {6 log.info(`enqueueing new URLs`);7 await enqueueLinks({8 globs: ['https://apify.com/*'],9 label: 'detail',10 });11});12
13router.addHandler('detail', async ({ request, page, log }) => {14 const title = await page.title();15 log.info(`${title}`, { url: request.loadedUrl });16
17 await Dataset.pushData({18 url: request.loadedUrl,19 title,20 });21});# configurations.idea.vscode.zed
# crawlee and apify storage foldersapify_storagecrawlee_storagestorage
# installed filesnode_modules
# git folder.gitroot = true
[*]indent_style = spaceindent_size = 4charset = utf-8trim_trailing_whitespace = trueinsert_final_newline = trueend_of_line = lfquote_type = single# This file tells Git which files shouldn't be added to source control
.DS_Store.idea.vscode.zeddistnode_modulesapify_storagestorage{ "printWidth": 120, "tabWidth": 4, "singleQuote": true}# Specify the base Docker image. You can read more about# the available images at https://crawlee.dev/docs/guides/docker-images# You can also use any other image from Docker Hub.FROM apify/actor-node-puppeteer-chrome:22-24.12.1
# Check preinstalled packagesRUN npm ls crawlee apify puppeteer playwright
# Copy just package.json and package-lock.json# to speed up the build using Docker layer cache.COPY package*.json Dockerfile ./
# Check Puppeteer version is the same as the one from base image.RUN node check-puppeteer-version.mjs
# Install NPM packages, skip optional and development dependencies to# keep the image small. Avoid logging too much and print the dependency# tree for debuggingRUN npm --quiet set progress=false \ && npm install --omit=dev --omit=optional \ && echo "Installed NPM packages:" \ && (npm list --omit=dev --all || true) \ && echo "Node.js version:" \ && node --version \ && echo "NPM version:" \ && npm --version \ && rm -r ~/.npm
# Next, copy the remaining files and directories with the source code.# Since we do this after NPM install, quick build will be really fast# for most source file changes.COPY . ./
# Run the image. If you know you won't need headful browsers,# you can remove the XVFB start script for a micro perf gain.CMD ./start_xvfb_and_run_cmd.sh && npm start --silent1import prettier from 'eslint-config-prettier';2
3import apify from '@apify/eslint-config/js.js';4
5// eslint-disable-next-line import/no-default-export6export default [{ ignores: ['**/dist'] }, ...apify, prettier];{ "name": "crawlee-puppeteer-javascript", "version": "0.0.1", "type": "module", "description": "This is an example of an Apify Actor.", "dependencies": { "apify": "^3.4.2", "crawlee": "^3.13.8", "puppeteer": "24.12.1" }, "devDependencies": { "@apify/eslint-config": "^1.0.0", "eslint": "^9.29.0", "eslint-config-prettier": "^10.1.5", "prettier": "^3.5.3" }, "scripts": { "start": "node src/main.js", "format": "prettier --write .", "format:check": "prettier --check .", "lint": "eslint", "lint:fix": "eslint --fix", "test": "echo \"Error: oops, the Actor has no tests yet, sad!\" && exit 1" }, "author": "It's not you it's me", "license": "ISC"}